In any CNN-based model, activations from top layers contain more global and abstract information (for example, high-level structures like a face), and bottom layers will contain local information (for example, low-level structures like eyes, nose, edges, and corners) about the image. We would want to leverage the top layers of a CNN for capturing the right representations for the content of an image. Hence, for the content loss, considering we will be using the pretrained VGG-16 model, we can define our loss function as the L2 norm (scaled and squared Euclidean distance) between the activations of a top layer (giving feature representations) computed over the target image, and the activations of the same layer computed over the generated image. Assuming we usually get feature representations relevant to the content of images from the top layers of a CNN, the generated image is expected to look similar to the base target image. The following snippet shows the function to compute the content loss:

def content_loss(base, combination):
    return K.sum(K.square(combination - base))